mayar-v2

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill utilizes npx -y mayar@latest to dynamically download and execute the Mayar CLI tool directly from the npm registry during setup and documentation retrieval.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with external API endpoints at api.mayar.id and api.mayar.club for payment processing and verification tasks.
  • [COMMAND_EXECUTION]: The agent is instructed to run local shell commands using the mayar CLI to verify merchant identity, set API keys, and manage webhooks.
  • [DATA_EXFILTRATION]: The skill identifies an indirect prompt injection surface during project reconnaissance.
  • Ingestion points: The agent reads project configuration files such as package.json, composer.json, and requirements.txt, and identifies the names of environment variables in .env files.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present.
  • Capability inventory: The agent has the capability to write files, execute shell commands via npx, and perform network operations.
  • Sanitization: No sanitization of ingested project metadata is performed.
  • [COMMAND_EXECUTION]: The skill generates and writes integration code files and modifies existing project configuration files (e.g., .env, .gitignore) to implement the payment flow.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 01:43 PM
Security Audit — agent-trust-hub — mayar-v2